Hi everyone overseas! ModelScope has launched its training service abroad. My LoRa training is all done using ModelScope. Thanks to the ModelScope team for providing the training infrastructure. Give it a try! https://www.modelscope.cn/aigc/modelTraining Welcome everyone to use Lora of Qwen Edit 2509 of Image Fusion, its performance is amazing！ Online running link： https://www.runninghub.ai/post/1983425100517187586?inviteCode=rh v1331 There are two ways to use it: 1. Use the prompts in the dataset to change the image directly. 2. Use the trigger word: " 重新照明 "。 （For example:重新照明,使用窗帘透光（柔和漫射）的光线对图片进行重新照明） Meaning: Relighting, using the soft, diffuse light from the curtains to relight the image. （I also uploaded the re light LoRAs for Kontext downloaded from the Internet. The sources are https://civit.ai/models/1779918 and https://hf.co/dong625/kontext loras/tree/main ） Instructions: Download the lora file（Qwen Edit Relight.safetensors to the models/loras folder. You also need this lora and use them together: https://huggingface.co/lightx2v/Qwen Image Lightning/tree/main This is the effect used by Lora: YouTube：https://youtu.be/GmDZmzoseFk Blibili：https://www.bilibili.com/video/BV11N…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy